This Open-Source canvas replaced my file system

What I Built

A spatial workspace that builds itself. I built a workspace that reads your files and decides what it should be.

An actual desktop app where you drop PDFs, spreadsheets, documents, notes, and images onto an infinite canvas, and it reads all of them, works out what connects them, and generates an interactive workspace shaped by what it found. Different files produce a different workspace. That's the whole point.

Here's the observation it started from. A folder is a container. It holds your files and it has never once understood them. Every piece of software we use to organize knowledge throws away the two most useful signals we give it: what's actually inside the documents, and how we chose to arrange them. So I tried to build the opposite. Something where both of those signals are the input.

It's called Aether Canvas. You drop files anywhere on the canvas. It reads what's inside them, discovers the relationships across formats, and builds a view around that context. Ask a question against the entire workspace and every answer traces back to the file and location it came from. Local-first, so the workspace never leaves your machine.

Demo

Why it's a desktop app and not a web demo: Aether is local-first by design. Your files stay on your machine, the workspace index is written to local storage, and nothing gets uploaded to a server to be processed and held. A hosted demo would mean the opposite of that. So instead of a link that borrows your files, there's an installer that runs on yours.

Try It

You don't have to build it. There's a signed installer - v1.0.0, Windows x64, no build step and no keys to paste in.

Download Aether Canvas for Windows (placeholder link - actual link from article)

Install it, drag a folder onto the empty canvas, and wait for the edges to appear. Then ask it something you'd normally have to open six files to answer.

Prefer to build from source:

git clone https://github.com/abbasmir12/aether-canvas
cd aether-canvas
npm install
npm run dev

Code

abbasmir12 / aether-canvas

A generative desktop where dropping files onto a spatial canvas builds living, AI-powered workspaces - powered by GPT-5.6. Space is the prompt.

Aether Canvas - Space is the prompt. A generative desktop where grouping ordinary files creates the mini-app you need.

OpenAI Build Week 2026 · Apps for Your Life · Built with Codex + GPT-5.6

Watch the demo · Devpost · See the product · Run Aether · GPT-5.6 · Build story

Five source files, four semantic streams, one GPT-generated interactive workspace-captured from the running Electron app.

Five files in. One living workspace out. A normal folder sees filenames. Aether sees the trip, project, course, budget, or plan they describe together.

CONCEPTUAL WORKFLOW · CLICK A CHAPTER

A hand-drawn explanation of the idea, not a screenshot of the application. Select any panel to inspect the real files, architecture, or product evidence behind it.

• 01 · Start with files - Open the exact sample files used in the demo.
• 02 · Understand context - Follow the implemented GPT-5.6 data flow.
• 03 · Become useful - See…

View on GitHub

How I Built It

The Input Surface is a Blank Canvas

There is no import wizard. No project setup, no schema to define, no tagging step, no folder structure to mirror. You drag files onto empty space and put them where they feel like they belong. That gesture is the only configuration the app asks for.

The core design decision - Position is information. When you put two files side by side, you mean something by it. Every tool I've used throws that signal away the moment you close the window.

Five Stages, Not One Prompt

I didn't want this to feel like "point an LLM at a folder and get a summary." So I split the work the way you'd actually split it.

1. 01 - The Drop - Files land on an infinite canvas. Any format, any arrangement, no setup.
2. 02 - The Read - GPT-5.6 extracts what each file actually contains. Not filenames, not metadata. The claims, figures, dates, and entities inside.
3. 03 - The Relate - Cross-format relationship discovery. A date in a PDF resolving a blank cell in a spreadsheet. A name tying a paragraph to a row.
4. 04 - The Render - The workspace view is derived, not templated. Trip, knowledge map, or operational board - whichever the content actually supports.
5. 05 - The Answer - Query the whole workspace at once. Every response carries the file and location it came from.

The Hard Part Was Not the Canvas

My first version linked anything that shared a keyword. Every node connected to every other node. Technically correct. Completely useless.

The relationship principle - The real problem is deciding when two files are actually related versus merely similar. That distinction is the entire difference between a workspace and a hairball.

What worked was making the model justify each edge before it could draw one. A relationship has to name the specific thing it's built on - this date, this figure, this entity - and that evidence has to resolve to a location in both files. If it can't point at both ends, the edge doesn't exist.

Similarity alone